Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‐
    -0.07
    986
    -0.07
    _UNITS
    -0.07
     CORE
    -0.06
     quantum
    -0.06
    فات
    -0.06
     ------------
    -0.06
    AXB
    -0.06
    AKE
    -0.06
    沖
    -0.06
    POSITIVE LOGITS
    шем
    0.07
    .TABLE
    0.06
     국
    0.06
    ่ได
    0.06
    ่า
    0.06
    @dynamic
    0.06
     Rhe
    0.06
    )))));
↵
    0.06
     >>=
    0.06
    ’nın
    0.06
    Act Density 0.002%

    No Known Activations